Mistral: Small 3.2 24B Instruct API

Mistral's Mistral: Small 3.2 24B Instruct, through an OpenAI-compatible API. 2 providers quote it now, and each request goes to the offer with the lowest estimated charge that meets your rules.

Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send mistral-small-3.2-24b-instruct as the model.
Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

Facts

Model name: mistral-small-3.2-24b-instruct
Maker: Mistral
Context window: 128K tokens
Input price: $0.100 to $0.100 per million tokens
Output price: $0.0040 to $0.320 per million tokens
Providers: 2 independent providers
Regions: eu, us

Providers

Pera: us, $0.100 input and $0.0040 output per million tokens, $0.100 cache read per million tokens, $0.000049 fee for each request, 128K tokens of context
SOKKAN: eu, $0.100 input and $0.320 output per million tokens, $0.100 cache read per million tokens, 128K tokens of context

Scores

HLE: 4.3, #219 of 273
GPQA: 50.5, #210 of 250
AA-LCR: 20.3, #212 of 237
SciCode: 28.6, #117 of 123
Terminal-Bench Hard: 6.8, #131 of 166
LiveCodeBench: 27.5, #97 of 130
AIME 2025: 27.0, #76 of 100
MMLU-Pro: 68.1, #97 of 133
τ²-Bench: 29.5, #138 of 169
IFBench: 33.5, #148 of 178
SimpleQA Verified: 19.1, #114 of 126

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral-small-3.2-24b-instruct",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Mistral: Small 3.2 24B Instruct?: Served by intent-router: each job goes to the cheapest healthy upstream for this model.
How much does Mistral: Small 3.2 24B Instruct cost?: Offers now ask $0.100 to $0.100 per million input tokens and $0.0040 to $0.320 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of Mistral: Small 3.2 24B Instruct?: The largest offer takes 128,000 input tokens. One job can generate up to 32,768 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Mistral: Small 3.2 24B Instruct do?: Its providers list Vision, JSON object, JSON schema, Frequency penalty, Presence penalty, Seed, Stop sequences, Top-p sampling, Text, Tools.
What inputs and outputs does Mistral: Small 3.2 24B Instruct support?: Text · Images → Text.
Which providers serve Mistral: Small 3.2 24B Instruct?: 2 independent providers quote it now, with 2 offers. The table above ranks them by the cost of a typical job.
How do I call Mistral: Small 3.2 24B Instruct?: Send "mistral-small-3.2-24b-instruct" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Mistral: Small 3.2 24B Instruct listed?: The exchange first listed it on 10/8/2026. This is not its release date.